INDEX

Explanations

phrases related to things being spread out or distributed

oai_token-act-pair · gpt-3.5-turbo

references to items being distributed or spread out

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sen

-0.79

acl

-0.72

Fight

-0.72

ests

-0.65

ocker

-0.63

asus

-0.62

 subord

-0.61

ises

-0.61

 Obesity

-0.61

chest

-0.60

POSITIVE LOGITS

 scattered

1.07

sheets

0.93

 scatter

0.85

 dispersed

0.83

 scattering

0.80

bom

0.78

mble

0.75

 across

0.73

Øª

0.73

 dispers

0.70

Activations Density 0.044%

phrases related to things being spread out or distributed

references to items being distributed or spread out

No Comments

No Known Activations